Alternatives and similar repositories for proj254:

Users that are interested in proj254 are comparing it to the libraries listed below

• hemingkx / SWIFT
  [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
  ☆45Updated 2 months ago
• NJUNLP / MCSD
  Multi-Candidate Speculative Decoding
  ☆35Updated 11 months ago
• mutonix / pyramidinfer
  ☆39Updated 4 months ago
• dongwonjo / FastKV
  Official Implementation of FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation
  ☆18Updated 2 weeks ago
• Zanette-Labs / SpeculativeRejection
  [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection
  ☆42Updated 5 months ago
• hemingkx / TokenSkip
  TokenSkip: Controllable Chain-of-Thought Compression in LLMs
  ☆128Updated last month
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆23Updated 2 months ago
• OpenSparseLLMs / Linear-MoE
  ☆75Updated this week
• abdelfattah-lab / TokenButler
  ☆20Updated 2 weeks ago
• Jingyu6 / speculative_prefill
  ☆21Updated 2 weeks ago
• raymin0223 / fast_robust_early_exit
  Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)
  ☆57Updated 6 months ago
• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆45Updated 6 months ago
• FFY0 / AdaKV
  The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
  ☆72Updated 2 months ago
• ArminAzizi98 / LaMDA
  ☆15Updated 5 months ago
• Lucky-Lance / Expert_Sparsity
  [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
  ☆87Updated 10 months ago
• hahahawu / Long-to-Short-via-Model-Merging
  Model merging is a highly efficient approach for long-to-short reasoning.
  ☆40Updated 3 weeks ago
• UNITES-Lab / MC-SMoE
  [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"
  ☆79Updated 10 months ago
• AkideLiu / MiniCache
  ☆8Updated 7 months ago
• ruipeterpan / specreason
  PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]
  ☆27Updated this week
• yangyifei729 / KVSharer
  Source code of paper ''KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing''
  ☆25Updated 5 months ago
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆75Updated last week
• zhiyuanhubj / LongRecipe
  LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
  ☆74Updated 6 months ago
• LiuXiaoxuanPKU / OSD
  ☆48Updated 4 months ago
• alessiodevoto / l2compress
  Code for the EMNLP24 paper "A simple and effective L2 norm based method for KV Cache compression."
  ☆11Updated 4 months ago
• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆181Updated 2 months ago
• SkyworkAI / skywork-o1-prm-inference
  ☆63Updated 4 months ago
• SempraETY / Pruning-via-Merging
  ☆18Updated 4 months ago
• sramshetty / ShortGPT
  Unofficial implementations of block/layer-wise pruning methods for LLMs.
  ☆68Updated 11 months ago
• sramshetty / mixture-of-depths
  An unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
  ☆35Updated 10 months ago
• horseee / CoT-Valve
  CoT-Valve: Length-Compressible Chain-of-Thought Tuning
  ☆65Updated 2 months ago